{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DJMIKT7XFZQK7S7GF7QGGTUB2Z","short_pith_number":"pith:DJMIKT7X","schema_version":"1.0","canonical_sha256":"1a58854ff72e60afcbe62fe0634e81d678c040d77d38b5a9893b09302b945d43","source":{"kind":"arxiv","id":"2307.08161","version":1},"attestation_state":"computed","paper":{"title":"Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Huy A. Nguyen, John Stamper, Steven Moore, Tianying Chen","submitted_at":"2023-07-16T22:12:10Z","abstract_excerpt":"Multiple-choice questions with item-writing flaws can negatively impact student learning and skew analytics. These flaws are often present in student-generated questions, making it difficult to assess their quality and suitability for classroom usage. Existing methods for evaluating multiple-choice questions often focus on machine readability metrics, without considering their intended use within course materials and their pedagogical implications. In this study, we compared the performance of a rule-based method we developed to a machine-learning based method utilizing GPT-4 for the task of a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.08161","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-16T22:12:10Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"304a8d5cb75f5fa458e05fac0903c1c4e2b9c4b247441ac71e0be16d97b1163b","abstract_canon_sha256":"9156b7b4d41f4088b4d3f522d8050a3b21c4b4d9beafdfcc163bc8c1dd161281"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:21.004643Z","signature_b64":"B/O1Ifk2Wgkcma1kR2O3b2jKJe963iEjHZ69oiSslK0DhkX6WNQ3pN4i/+kllYFBhcRjP+TkwDDHGyhYNDpcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a58854ff72e60afcbe62fe0634e81d678c040d77d38b5a9893b09302b945d43","last_reissued_at":"2026-07-05T06:31:21.004294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:21.004294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Quality of Multiple-Choice Questions Using GPT-4 and Rule-Based Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Huy A. Nguyen, John Stamper, Steven Moore, Tianying Chen","submitted_at":"2023-07-16T22:12:10Z","abstract_excerpt":"Multiple-choice questions with item-writing flaws can negatively impact student learning and skew analytics. These flaws are often present in student-generated questions, making it difficult to assess their quality and suitability for classroom usage. Existing methods for evaluating multiple-choice questions often focus on machine readability metrics, without considering their intended use within course materials and their pedagogical implications. In this study, we compared the performance of a rule-based method we developed to a machine-learning based method utilizing GPT-4 for the task of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08161","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.08161/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.08161","created_at":"2026-07-05T06:31:21.004361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08161v1","created_at":"2026-07-05T06:31:21.004361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08161","created_at":"2026-07-05T06:31:21.004361+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJMIKT7XFZQK","created_at":"2026-07-05T06:31:21.004361+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJMIKT7XFZQK7S7G","created_at":"2026-07-05T06:31:21.004361+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJMIKT7X","created_at":"2026-07-05T06:31:21.004361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z","json":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z.json","graph_json":"https://pith.science/api/pith-number/DJMIKT7XFZQK7S7GF7QGGTUB2Z/graph.json","events_json":"https://pith.science/api/pith-number/DJMIKT7XFZQK7S7GF7QGGTUB2Z/events.json","paper":"https://pith.science/paper/DJMIKT7X"},"agent_actions":{"view_html":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z","download_json":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z.json","view_paper":"https://pith.science/paper/DJMIKT7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08161&json=true","fetch_graph":"https://pith.science/api/pith-number/DJMIKT7XFZQK7S7GF7QGGTUB2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/DJMIKT7XFZQK7S7GF7QGGTUB2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z/action/storage_attestation","attest_author":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z/action/author_attestation","sign_citation":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z/action/citation_signature","submit_replication":"https://pith.science/pith/DJMIKT7XFZQK7S7GF7QGGTUB2Z/action/replication_record"}},"created_at":"2026-07-05T06:31:21.004361+00:00","updated_at":"2026-07-05T06:31:21.004361+00:00"}